LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 3.2 3B Instruct by meta-llama

 »  All LLMs  »  meta-llama  »  Llama 3.2 3B Instruct   URL Share it on

  1713021   
  Arxiv:2204.05149   Arxiv:2405.16406   Autotrain compatible   Conversational   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   Instruct   It   Llama   Llama-3   Meta   Pt   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct 

Llama 3.2 3B Instruct Benchmarks

MMLU Pro: 24.39
GPQA: 3.8
MUSR: 1.37
BBH: 24.06
IFEval: 73.93 vs 88 (so35)-16%
MATH Lvl 5: 17.67
LLME Score: 0.47264
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.2 3B Instruct (meta-llama/Llama-3.2-3B-Instruct)

Llama 3.2 3B Instruct Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
multilingual dialogue, knowledge retrieval, summarization, AI powered writing assistants, query and prompt rewriting
Limitations:
Use in any manner that violates applicable laws or regulations
Supported Languages 
English (officially supported), German (officially supported), French (officially supported), Italian (officially supported), Portuguese (officially supported), Hindi (officially supported), Spanish (officially supported), Thai (officially supported)
Training Details 
Data Sources:
publicly available online data
Data Volume:
up to 9 trillion tokens
Methodology:
Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO)
Context Length:
128000
Hardware Used:
H100-80GB GPUs (TDP of 700W)
Model Architecture:
Auto-regressive transformer with Grouped-Query Attention (GQA)
Input Output 
Accepted Modalities:
Multilingual Text
Output Format:
Multilingual Text and code
LLM NameLlama 3.2 3B Instruct
Repository 🤗https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct 
Model Size3b
Required VRAM6.5 GB
Updated2025-05-31
Maintainermeta-llama
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen de fr it pt hi es th
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3.2 3B Instruct

Model
Likes
Downloads
VRAM
...2 3B Instruct Unsloth Bnb 4bit101387322 GB
....1 Llama 3.2 3B It Grpo 250404616136 GB
Llama 3.2 3B Instruct GGUF122350250 GB
Llama 3.2 3B Unsloth Bnb 4bit1116212 GB
Llama 3.2 3B Instruct Bnb 4bit18701812 GB
Orca Mini V9 0 3B Instruct5216 GB
Gladiator Mini Exp 1211 3B066 GB
...r Mini Exp 1221 3B Instruct V2086 GB
...ator Mini Exp 1222 3B Instruct056 GB
...ator Mini Exp 1221 3B Instruct0106 GB

Best Alternatives to Llama 3.2 3B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek R1 Distill Llama 3B128K / 6.5 GB43011
Orpheus 3B 0.1 Pretrained128K / 6.6 GB108830
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB112
Llama 3.2 3B Instruct128K / 6.5 GB20905166
Zeitgeist 3B V1128K / 6.5 GB1055
Llama 3.2 3B Bespoke Thought128K / 6.4 GB4093
ReasoningCore 3B T1 1128K / 6.5 GB441
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB480
Llama 3.2 3B ToxicKod128K / 6.4 GB92
FuseChat Llama 3.2 3B Instruct128K / 6.5 GB337

Rank the Llama 3.2 3B Instruct Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 47753 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer